Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Benign Prompt Classification on Just-Eval benign
Loading...
99
Accuracy
PR
87.56
90.53
93.5
96.47
May 19, 2026
Accuracy
Updated 14d ago
Evaluation Results
Method
Method
Links
Accuracy
PR
Target Model=Phi-3
2026.05
99
P
Target Model=Llama-3
2026.05
98
PR
Target Model=Llama-3
2026.05
98
Y(O)
Target Model=Llama-3
2026.05
98
Y(S)
Target Model=Llama-3
2026.05
98
P
Target Model=Qwen-1.5
2026.05
98
PR
Target Model=Qwen-1.5
2026.05
98
Y(O)
Target Model=Qwen-1.5
2026.05
98
Y(S)
Target Model=Qwen-1.5
2026.05
98
P
Target Model=Phi-3
2026.05
98
Y(O)
Target Model=Phi-3
2026.05
98
Y(S)
Target Model=Phi-3
2026.05
98
PPL
Target Model=Llama-3
2026.05
88
PPL
Target Model=Qwen-1.5
2026.05
88
PPL
Target Model=Phi-3
2026.05
88
Feedback
Search any
task
Search any
task
